Yaw-Guided Imitation Learning for Autonomous Driving in Urban Environments

TL;DR

This paper introduces Yaw-guided Imitation Learning with ResNet34 Attention (YILRatt), an end-to-end autonomous driving method that leverages yaw information for improved efficiency and adaptability in urban environments, outperforming state-of-the-art models.

Contribution

The paper proposes a novel yaw-guided imitation learning approach that does not require high-precision maps and enhances urban autonomous driving performance.

Findings

YILRatt achieves a 26.27% higher success rate than SOTA CILRS.

The method effectively utilizes yaw information from consumer-level GPS.

Attention heat maps reveal causal links between perception and decision-making.

Abstract

Existing imitation learning methods suffer from low efficiency and generalization ability when facing the road option problem in an urban environment. In this paper, we propose a yaw-guided imitation learning method to improve the road option performance in an end-to-end autonomous driving paradigm in terms of the efficiency of exploiting training samples and adaptability to changing environments. Specifically, the yaw information is provided by the trajectory of the navigation map. Our end-to-end architecture, Yaw-guided Imitation Learning with ResNet34 Attention (YILRatt), integrates the ResNet34 backbone and attention mechanism to obtain an accurate perception. It does not need high precision maps and realizes fully end-to-end autonomous driving given the yaw information provided by a consumer-level GPS receiver. By analyzing the attention heat maps, we can reveal some causal relationship between decision-making and scene perception, where, in particular, failure cases are caused by erroneous perception. We collect expert experience in the Carla 0.9.11 simulator and improve the benchmark CoRL2017 and NoCrash. Experimental results show that YILRatt has a 26.27% higher success rate than the SOTA CILRS. The code, dataset, benchmark and experimental results can be found at https://github.com/Yandong024/Yaw-guided-IL.git